Dmitry,
On Mon, 19 Aug 2019, Dmitry Safonov wrote:
> On 8/18/19 5:21 PM, Thomas Gleixner wrote:
> > That means your timens_to_host() and host_to_timens() conversion functions
> > should just use that special VDSO page and do the same array based
> > unconditional add/sub of the clock specific
Hi Thomas,
On 8/18/19 5:21 PM, Thomas Gleixner wrote:
[..]
> I'm happy to review well written stuff which makes progress and takes
> review comments into account or the submitter discusses them for
> resolution.
Thanks again for both your and Andy time!
[..]
> Coming back to Andy's idea. Create
On Sun, 18 Aug 2019, Thomas Gleixner wrote:
> On Sun, 18 Aug 2019, Thomas Gleixner wrote:
> >
> > Patch below. I tested this with the normal order and by installing a
> > 'timens' page unconditionally for all processes. I'll reply with the timens
> > testing hacks so you can see what I did.
>
>
On Sun, 18 Aug 2019, Thomas Gleixner wrote:
>
> Patch below. I tested this with the normal order and by installing a
> 'timens' page unconditionally for all processes. I'll reply with the timens
> testing hacks so you can see what I did.
First hack...
Thanks,
tglx
8<-
Dmitry,
On Fri, 16 Aug 2019, Dmitry Safonov wrote:
> On 8/16/19 9:10 PM, Thomas Gleixner wrote:
> > On Fri, 16 Aug 2019, Andy Lutomirski wrote:
> [..]
> >> I'm unconvinced that any of this magic is wise. I think you should make a
> >> special timens vvar page that causes the normal fastpath to
Hi Andy, Thomas,
thank you very much for your time and the reviews, appreciate that.
On 8/16/19 9:10 PM, Thomas Gleixner wrote:
> On Fri, 16 Aug 2019, Andy Lutomirski wrote:
[..]
>> I'm unconvinced that any of this magic is wise. I think you should make a
>> special timens vvar page that causes
On Fri, 16 Aug 2019, Andy Lutomirski wrote:
> On 8/15/19 9:38 AM, Dmitry Safonov wrote:
> > As it has been discussed on timens RFC, adding a new conditional branch
> > `if (inside_time_ns)` on VDSO for all processes is undesirable.
> > It will add a penalty for everybody as branch predictor may
On 8/15/19 9:38 AM, Dmitry Safonov wrote:
As it has been discussed on timens RFC, adding a new conditional branch
`if (inside_time_ns)` on VDSO for all processes is undesirable.
It will add a penalty for everybody as branch predictor may mispredict
the jump. Also there are instruction cache
As it has been discussed on timens RFC, adding a new conditional branch
`if (inside_time_ns)` on VDSO for all processes is undesirable.
It will add a penalty for everybody as branch predictor may mispredict
the jump. Also there are instruction cache lines wasted on cmp/jmp.
Those effects of
9 matches
Mail list logo